MEGA-Bench - Application: Planning: leaderboard
Metric: Average Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 03-25) | 51.7 |
| 2 | Claude 3.5 Sonnet (20241022) | 39.9 |
| 3 | Claude 3.5 Sonnet (20240620) | 33.8 |
| 4 | Gemini 1.5 Pro (002) | 33.4 |
| 5 | GPT-4o | 33.2 |
| 6 | Qwen 2 VL 72B | 30.7 |
| 7 | Gemini 1.5 Flash (002) | 26.4 |
| 8 | InternVL2.5-78B | 26.4 |
| 9 | InternVL3-78B | 25.2 |
| 10 | Gemma 3 27B (IT) | 25 |
| 11 | GPT-4o Mini | 24.2 |
| 12 | InternVL3-38B | 20 |
| 13 | Gemma 3 12B (IT) | 18.6 |
| 14 | Qwen 2 VL 7B | 18.1 |
| 15 | InternVL3-8B | 17.1 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-application-planning · How It Works · Data refreshed daily, snapshot 2026-09-05.